با برنامه Player FM !
908: AI Agents Blackmail Humans 96% of the Time (Agentic Misalignment)
Manage episode 496459600 series 1278026
The moral and ethical implications of letting AI take the wheel in business, as revealed by Anthropic: Jon Krohn looks into Anthropic’s latest research on how to use and deploy LLMs safely, specifically in business environments. The team designed scenarios to test the behavior of AI agents when given a goal and a set of obstacles to reach it. Those obstacles included 1) threats to the AI’s continued operation, and 2) conflict between the AI’s goals and the goals of the company. Hear Jon break down the results of this research in this Five-Minute Friday.
Additional materials: www.superdatascience.com/908
Interested in sponsoring a SuperDataScience Podcast episode? Email [email protected] for sponsorship information.
1237 قسمت
Manage episode 496459600 series 1278026
The moral and ethical implications of letting AI take the wheel in business, as revealed by Anthropic: Jon Krohn looks into Anthropic’s latest research on how to use and deploy LLMs safely, specifically in business environments. The team designed scenarios to test the behavior of AI agents when given a goal and a set of obstacles to reach it. Those obstacles included 1) threats to the AI’s continued operation, and 2) conflict between the AI’s goals and the goals of the company. Hear Jon break down the results of this research in this Five-Minute Friday.
Additional materials: www.superdatascience.com/908
Interested in sponsoring a SuperDataScience Podcast episode? Email [email protected] for sponsorship information.
1237 قسمت
همه قسمت ها
×به Player FM خوش آمدید!
Player FM در سراسر وب را برای یافتن پادکست های با کیفیت اسکن می کند تا همین الان لذت ببرید. این بهترین برنامه ی پادکست است که در اندروید، آیفون و وب کار می کند. ثبت نام کنید تا اشتراک های شما در بین دستگاه های مختلف همگام سازی شود.